QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
Top Cited Papers
- 9 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 436-450
Abstract
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a new scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and better rate-distortion performance than existing baseline methods.Keywords
All Related Versions
Funding Information
- National Cancer Institute (R01CA277839)
This publication has 36 references indexed in Scilit:
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Microsoft COCO: Common Objects in Context2014
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Elements of Information Theory2001
- The MPEG-4 fine-grained scalable video coding method for multimedia streaming over IPIEEE Transactions on Multimedia, 2001
- Vision Models and Applications to Image and Video Processing2001
- Keeping the neural networks simple by minimizing the description length of the weights1993
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992
- A Method for the Construction of Minimum-Redundancy CodesProceedings of the IRE, 1952